Update Linux to v5.10.109

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz

Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/mm/gup.c b/mm/gup.c
index 3ef7695..6cb7d8a 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -19,7 +19,6 @@
 #include <linux/sched/mm.h>
 
 #include <asm/mmu_context.h>
-#include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 
 #include "internal.h"
@@ -29,8 +28,222 @@ struct follow_page_context {
 	unsigned int page_mask;
 };
 
+static void hpage_pincount_add(struct page *page, int refs)
+{
+	VM_BUG_ON_PAGE(!hpage_pincount_available(page), page);
+	VM_BUG_ON_PAGE(page != compound_head(page), page);
+
+	atomic_add(refs, compound_pincount_ptr(page));
+}
+
+static void hpage_pincount_sub(struct page *page, int refs)
+{
+	VM_BUG_ON_PAGE(!hpage_pincount_available(page), page);
+	VM_BUG_ON_PAGE(page != compound_head(page), page);
+
+	atomic_sub(refs, compound_pincount_ptr(page));
+}
+
+/* Equivalent to calling put_page() @refs times. */
+static void put_page_refs(struct page *page, int refs)
+{
+#ifdef CONFIG_DEBUG_VM
+	if (VM_WARN_ON_ONCE_PAGE(page_ref_count(page) < refs, page))
+		return;
+#endif
+
+	/*
+	 * Calling put_page() for each ref is unnecessarily slow. Only the last
+	 * ref needs a put_page().
+	 */
+	if (refs > 1)
+		page_ref_sub(page, refs - 1);
+	put_page(page);
+}
+
+/*
+ * Return the compound head page with ref appropriately incremented,
+ * or NULL if that failed.
+ */
+static inline struct page *try_get_compound_head(struct page *page, int refs)
+{
+	struct page *head = compound_head(page);
+
+	if (WARN_ON_ONCE(page_ref_count(head) < 0))
+		return NULL;
+	if (unlikely(!page_cache_add_speculative(head, refs)))
+		return NULL;
+
+	/*
+	 * At this point we have a stable reference to the head page; but it
+	 * could be that between the compound_head() lookup and the refcount
+	 * increment, the compound page was split, in which case we'd end up
+	 * holding a reference on a page that has nothing to do with the page
+	 * we were given anymore.
+	 * So now that the head page is stable, recheck that the pages still
+	 * belong together.
+	 */
+	if (unlikely(compound_head(page) != head)) {
+		put_page_refs(head, refs);
+		return NULL;
+	}
+
+	return head;
+}
+
+/*
+ * try_grab_compound_head() - attempt to elevate a page's refcount, by a
+ * flags-dependent amount.
+ *
+ * "grab" names in this file mean, "look at flags to decide whether to use
+ * FOLL_PIN or FOLL_GET behavior, when incrementing the page's refcount.
+ *
+ * Either FOLL_PIN or FOLL_GET (or neither) must be set, but not both at the
+ * same time. (That's true throughout the get_user_pages*() and
+ * pin_user_pages*() APIs.) Cases:
+ *
+ *    FOLL_GET: page's refcount will be incremented by 1.
+ *    FOLL_PIN: page's refcount will be incremented by GUP_PIN_COUNTING_BIAS.
+ *
+ * Return: head page (with refcount appropriately incremented) for success, or
+ * NULL upon failure. If neither FOLL_GET nor FOLL_PIN was set, that's
+ * considered failure, and furthermore, a likely bug in the caller, so a warning
+ * is also emitted.
+ */
+static __maybe_unused struct page *try_grab_compound_head(struct page *page,
+							  int refs,
+							  unsigned int flags)
+{
+	if (flags & FOLL_GET)
+		return try_get_compound_head(page, refs);
+	else if (flags & FOLL_PIN) {
+		int orig_refs = refs;
+
+		/*
+		 * Can't do FOLL_LONGTERM + FOLL_PIN with CMA in the gup fast
+		 * path, so fail and let the caller fall back to the slow path.
+		 */
+		if (unlikely(flags & FOLL_LONGTERM) &&
+				is_migrate_cma_page(page))
+			return NULL;
+
+		/*
+		 * CAUTION: Don't use compound_head() on the page before this
+		 * point, the result won't be stable.
+		 */
+		page = try_get_compound_head(page, refs);
+		if (!page)
+			return NULL;
+
+		/*
+		 * When pinning a compound page of order > 1 (which is what
+		 * hpage_pincount_available() checks for), use an exact count to
+		 * track it, via hpage_pincount_add/_sub().
+		 *
+		 * However, be sure to *also* increment the normal page refcount
+		 * field at least once, so that the page really is pinned.
+		 */
+		if (hpage_pincount_available(page))
+			hpage_pincount_add(page, refs);
+		else
+			page_ref_add(page, refs * (GUP_PIN_COUNTING_BIAS - 1));
+
+		mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_ACQUIRED,
+				    orig_refs);
+
+		return page;
+	}
+
+	WARN_ON_ONCE(1);
+	return NULL;
+}
+
+static void put_compound_head(struct page *page, int refs, unsigned int flags)
+{
+	if (flags & FOLL_PIN) {
+		mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_RELEASED,
+				    refs);
+
+		if (hpage_pincount_available(page))
+			hpage_pincount_sub(page, refs);
+		else
+			refs *= GUP_PIN_COUNTING_BIAS;
+	}
+
+	put_page_refs(page, refs);
+}
+
 /**
- * put_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
+ * try_grab_page() - elevate a page's refcount by a flag-dependent amount
+ *
+ * This might not do anything at all, depending on the flags argument.
+ *
+ * "grab" names in this file mean, "look at flags to decide whether to use
+ * FOLL_PIN or FOLL_GET behavior, when incrementing the page's refcount.
+ *
+ * @page:    pointer to page to be grabbed
+ * @flags:   gup flags: these are the FOLL_* flag values.
+ *
+ * Either FOLL_PIN or FOLL_GET (or neither) may be set, but not both at the same
+ * time. Cases:
+ *
+ *    FOLL_GET: page's refcount will be incremented by 1.
+ *    FOLL_PIN: page's refcount will be incremented by GUP_PIN_COUNTING_BIAS.
+ *
+ * Return: true for success, or if no action was required (if neither FOLL_PIN
+ * nor FOLL_GET was set, nothing is done). False for failure: FOLL_GET or
+ * FOLL_PIN was set, but the page could not be grabbed.
+ */
+bool __must_check try_grab_page(struct page *page, unsigned int flags)
+{
+	WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == (FOLL_GET | FOLL_PIN));
+
+	if (flags & FOLL_GET)
+		return try_get_page(page);
+	else if (flags & FOLL_PIN) {
+		int refs = 1;
+
+		page = compound_head(page);
+
+		if (WARN_ON_ONCE(page_ref_count(page) <= 0))
+			return false;
+
+		if (hpage_pincount_available(page))
+			hpage_pincount_add(page, 1);
+		else
+			refs = GUP_PIN_COUNTING_BIAS;
+
+		/*
+		 * Similar to try_grab_compound_head(): even if using the
+		 * hpage_pincount_add/_sub() routines, be sure to
+		 * *also* increment the normal page refcount field at least
+		 * once, so that the page really is pinned.
+		 */
+		page_ref_add(page, refs);
+
+		mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_ACQUIRED, 1);
+	}
+
+	return true;
+}
+
+/**
+ * unpin_user_page() - release a dma-pinned page
+ * @page:            pointer to page to be released
+ *
+ * Pages that were pinned via pin_user_pages*() must be released via either
+ * unpin_user_page(), or one of the unpin_user_pages*() routines. This is so
+ * that such pages can be separately tracked and uniquely handled. In
+ * particular, interactions with RDMA and filesystems need special handling.
+ */
+void unpin_user_page(struct page *page)
+{
+	put_compound_head(compound_head(page), 1, FOLL_PIN);
+}
+EXPORT_SYMBOL(unpin_user_page);
+
+/**
+ * unpin_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
  * @pages:  array of pages to be maybe marked dirty, and definitely released.
  * @npages: number of pages in the @pages array.
  * @make_dirty: whether to mark the pages dirty
@@ -40,19 +253,19 @@ struct follow_page_context {
  *
  * For each page in the @pages array, make that page (or its head page, if a
  * compound page) dirty, if @make_dirty is true, and if the page was previously
- * listed as clean. In any case, releases all pages using put_user_page(),
- * possibly via put_user_pages(), for the non-dirty case.
+ * listed as clean. In any case, releases all pages using unpin_user_page(),
+ * possibly via unpin_user_pages(), for the non-dirty case.
  *
- * Please see the put_user_page() documentation for details.
+ * Please see the unpin_user_page() documentation for details.
  *
  * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is
  * required, then the caller should a) verify that this is really correct,
  * because _lock() is usually required, and b) hand code it:
- * set_page_dirty_lock(), put_user_page().
+ * set_page_dirty_lock(), unpin_user_page().
  *
  */
-void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
-			       bool make_dirty)
+void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages,
+				 bool make_dirty)
 {
 	unsigned long index;
 
@@ -63,7 +276,7 @@ void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
 	 */
 
 	if (!make_dirty) {
-		put_user_pages(pages, npages);
+		unpin_user_pages(pages, npages);
 		return;
 	}
 
@@ -91,33 +304,40 @@ void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
 		 */
 		if (!PageDirty(page))
 			set_page_dirty_lock(page);
-		put_user_page(page);
+		unpin_user_page(page);
 	}
 }
-EXPORT_SYMBOL(put_user_pages_dirty_lock);
+EXPORT_SYMBOL(unpin_user_pages_dirty_lock);
 
 /**
- * put_user_pages() - release an array of gup-pinned pages.
+ * unpin_user_pages() - release an array of gup-pinned pages.
  * @pages:  array of pages to be marked dirty and released.
  * @npages: number of pages in the @pages array.
  *
- * For each page in the @pages array, release the page using put_user_page().
+ * For each page in the @pages array, release the page using unpin_user_page().
  *
- * Please see the put_user_page() documentation for details.
+ * Please see the unpin_user_page() documentation for details.
  */
-void put_user_pages(struct page **pages, unsigned long npages)
+void unpin_user_pages(struct page **pages, unsigned long npages)
 {
 	unsigned long index;
 
 	/*
+	 * If this WARN_ON() fires, then the system *might* be leaking pages (by
+	 * leaving them pinned), but probably not. More likely, gup/pup returned
+	 * a hard -ERRNO error to the caller, who erroneously passed it here.
+	 */
+	if (WARN_ON(IS_ERR_VALUE(npages)))
+		return;
+	/*
 	 * TODO: this can be optimized for huge pages: if a series of pages is
 	 * physically contiguous and part of the same compound page, then a
 	 * single operation to the head page should suffice.
 	 */
 	for (index = 0; index < npages; index++)
-		put_user_page(pages[index]);
+		unpin_user_page(pages[index]);
 }
-EXPORT_SYMBOL(put_user_pages);
+EXPORT_SYMBOL(unpin_user_pages);
 
 #ifdef CONFIG_MMU
 static struct page *no_page_table(struct vm_area_struct *vma,
@@ -131,7 +351,8 @@ static struct page *no_page_table(struct vm_area_struct *vma,
 	 * But we can only make this optimization where a hole would surely
 	 * be zero-filled if handle_mm_fault() actually did handle it.
 	 */
-	if ((flags & FOLL_DUMP) && (!vma->vm_ops || !vma->vm_ops->fault))
+	if ((flags & FOLL_DUMP) &&
+			(vma_is_anonymous(vma) || !vma->vm_ops->fault))
 		return ERR_PTR(-EFAULT);
 	return NULL;
 }
@@ -161,22 +382,13 @@ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address,
 }
 
 /*
- * FOLL_FORCE or a forced COW break can write even to unwritable pte's,
- * but only after we've gone through a COW cycle and they are dirty.
+ * FOLL_FORCE can write to even unwritable pte's, but only
+ * after we've gone through a COW cycle and they are dirty.
  */
 static inline bool can_follow_write_pte(pte_t pte, unsigned int flags)
 {
-	return pte_write(pte) || ((flags & FOLL_COW) && pte_dirty(pte));
-}
-
-/*
- * A (separate) COW fault might break the page the other way and
- * get_user_pages() would return the page from what is now the wrong
- * VM. So we need to force a COW break at GUP time even for reads.
- */
-static inline bool should_force_cow_break(struct vm_area_struct *vma, unsigned int flags)
-{
-	return is_cow_mapping(vma->vm_flags) && (flags & FOLL_GET);
+	return pte_write(pte) ||
+		((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte));
 }
 
 static struct page *follow_page_pte(struct vm_area_struct *vma,
@@ -187,7 +399,12 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 	struct page *page;
 	spinlock_t *ptl;
 	pte_t *ptep, pte;
+	int ret;
 
+	/* FOLL_GET and FOLL_PIN are mutually exclusive. */
+	if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) ==
+			 (FOLL_PIN | FOLL_GET)))
+		return ERR_PTR(-EINVAL);
 retry:
 	if (unlikely(pmd_bad(*pmd)))
 		return no_page_table(vma, flags);
@@ -220,10 +437,11 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 	}
 
 	page = vm_normal_page(vma, address, pte);
-	if (!page && pte_devmap(pte) && (flags & FOLL_GET)) {
+	if (!page && pte_devmap(pte) && (flags & (FOLL_GET | FOLL_PIN))) {
 		/*
-		 * Only return device mapping pages in the FOLL_GET case since
-		 * they are only valid while holding the pgmap reference.
+		 * Only return device mapping pages in the FOLL_GET or FOLL_PIN
+		 * case since they are only valid while holding the pgmap
+		 * reference.
 		 */
 		*pgmap = get_dev_pagemap(pte_pfn(pte), *pgmap);
 		if (*pgmap)
@@ -240,8 +458,6 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 		if (is_zero_pfn(pte_pfn(pte))) {
 			page = pte_page(pte);
 		} else {
-			int ret;
-
 			ret = follow_pfn_pte(vma, address, ptep, flags);
 			page = ERR_PTR(ret);
 			goto out;
@@ -249,7 +465,6 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 	}
 
 	if (flags & FOLL_SPLIT && PageTransCompound(page)) {
-		int ret;
 		get_page(page);
 		pte_unmap_unlock(ptep, ptl);
 		lock_page(page);
@@ -261,9 +476,21 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 		goto retry;
 	}
 
-	if (flags & FOLL_GET) {
-		if (unlikely(!try_get_page(page))) {
-			page = ERR_PTR(-ENOMEM);
+	/* try_grab_page() does nothing unless FOLL_GET or FOLL_PIN is set. */
+	if (unlikely(!try_grab_page(page, flags))) {
+		page = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+	/*
+	 * We need to make the page accessible if and only if we are going
+	 * to access its content (the FOLL_PIN case).  Please see
+	 * Documentation/core-api/pin_user_pages.rst for details.
+	 */
+	if (flags & FOLL_PIN) {
+		ret = arch_make_page_accessible(page);
+		if (ret) {
+			unpin_user_page(page);
+			page = ERR_PTR(ret);
 			goto out;
 		}
 	}
@@ -332,7 +559,7 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 	pmdval = READ_ONCE(*pmd);
 	if (pmd_none(pmdval))
 		return no_page_table(vma, flags);
-	if (pmd_huge(pmdval) && vma->vm_flags & VM_HUGETLB) {
+	if (pmd_huge(pmdval) && is_vm_hugetlb_page(vma)) {
 		page = follow_huge_pmd(mm, address, pmd, flags);
 		if (page)
 			return page;
@@ -357,7 +584,7 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 		pmdval = READ_ONCE(*pmd);
 		/*
 		 * MADV_DONTNEED may convert the pmd to null because
-		 * mmap_sem is held in read mode
+		 * mmap_lock is held in read mode
 		 */
 		if (pmd_none(pmdval))
 			return no_page_table(vma, flags);
@@ -442,7 +669,7 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma,
 	pud = pud_offset(p4dp, address);
 	if (pud_none(*pud))
 		return no_page_table(vma, flags);
-	if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
+	if (pud_huge(*pud) && is_vm_hugetlb_page(vma)) {
 		page = follow_huge_pud(mm, address, pud, flags);
 		if (page)
 			return page;
@@ -527,7 +754,7 @@ static struct page *follow_page_mask(struct vm_area_struct *vma,
 	/* make this handle hugepd */
 	page = follow_huge_addr(mm, address, flags & FOLL_WRITE);
 	if (!IS_ERR(page)) {
-		BUG_ON(flags & FOLL_GET);
+		WARN_ON_ONCE(flags & (FOLL_GET | FOLL_PIN));
 		return page;
 	}
 
@@ -608,7 +835,7 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address,
 			goto unmap;
 		*page = pte_page(*pte);
 	}
-	if (unlikely(!try_get_page(*page))) {
+	if (unlikely(!try_grab_page(*page, gup_flags))) {
 		ret = -ENOMEM;
 		goto unmap;
 	}
@@ -620,12 +847,12 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address,
 }
 
 /*
- * mmap_sem must be held on entry.  If @nonblocking != NULL and
- * *@flags does not include FOLL_NOWAIT, the mmap_sem may be released.
- * If it is, *@nonblocking will be set to 0 and -EBUSY returned.
+ * mmap_lock must be held on entry.  If @locked != NULL and *@flags
+ * does not include FOLL_NOWAIT, the mmap_lock may be released.  If it
+ * is, *@locked will be set to 0 and -EBUSY returned.
  */
-static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
-		unsigned long address, unsigned int *flags, int *nonblocking)
+static int faultin_page(struct vm_area_struct *vma,
+		unsigned long address, unsigned int *flags, int *locked)
 {
 	unsigned int fault_flags = 0;
 	vm_fault_t ret;
@@ -637,16 +864,19 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
 		fault_flags |= FAULT_FLAG_WRITE;
 	if (*flags & FOLL_REMOTE)
 		fault_flags |= FAULT_FLAG_REMOTE;
-	if (nonblocking)
-		fault_flags |= FAULT_FLAG_ALLOW_RETRY;
+	if (locked)
+		fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 	if (*flags & FOLL_NOWAIT)
 		fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT;
 	if (*flags & FOLL_TRIED) {
-		VM_WARN_ON_ONCE(fault_flags & FAULT_FLAG_ALLOW_RETRY);
+		/*
+		 * Note: FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_TRIED
+		 * can co-exist
+		 */
 		fault_flags |= FAULT_FLAG_TRIED;
 	}
 
-	ret = handle_mm_fault(vma, address, fault_flags);
+	ret = handle_mm_fault(vma, address, fault_flags, NULL);
 	if (ret & VM_FAULT_ERROR) {
 		int err = vm_fault_to_errno(ret, *flags);
 
@@ -655,16 +885,9 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
 		BUG();
 	}
 
-	if (tsk) {
-		if (ret & VM_FAULT_MAJOR)
-			tsk->maj_flt++;
-		else
-			tsk->min_flt++;
-	}
-
 	if (ret & VM_FAULT_RETRY) {
-		if (nonblocking && !(fault_flags & FAULT_FLAG_RETRY_NOWAIT))
-			*nonblocking = 0;
+		if (locked && !(fault_flags & FAULT_FLAG_RETRY_NOWAIT))
+			*locked = 0;
 		return -EBUSY;
 	}
 
@@ -731,7 +954,6 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
 
 /**
  * __get_user_pages() - pin user pages in memory
- * @tsk:	task_struct of target task
  * @mm:		mm_struct of target mm
  * @start:	starting user address
  * @nr_pages:	number of pages from start to pin
@@ -741,15 +963,22 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
  *		only intends to ensure the pages are faulted in.
  * @vmas:	array of pointers to vmas corresponding to each page.
  *		Or NULL if the caller does not require them.
- * @nonblocking: whether waiting for disk IO or mmap_sem contention
+ * @locked:     whether we're still with the mmap_lock held
  *
- * Returns number of pages pinned. This may be fewer than the number
- * requested. If nr_pages is 0 or negative, returns 0. If no pages
- * were pinned, returns -errno. Each page returned must be released
- * with a put_page() call when it is finished with. vmas will only
- * remain valid while mmap_sem is held.
+ * Returns either number of pages pinned (which may be less than the
+ * number requested), or an error. Details about the return value:
  *
- * Must be called with mmap_sem held.  It may be released.  See below.
+ * -- If nr_pages is 0, returns 0.
+ * -- If nr_pages is >0, but no pages were pinned, returns -errno.
+ * -- If nr_pages is >0, and some pages were pinned, returns the number of
+ *    pages pinned. Again, this may be less than nr_pages.
+ * -- 0 return value is possible when the fault would need to be retried.
+ *
+ * The caller is responsible for releasing returned @pages, via put_page().
+ *
+ * @vmas are valid only as long as mmap_lock is held.
+ *
+ * Must be called with mmap_lock held.  It may be released.  See below.
  *
  * __get_user_pages walks a process's page tables and takes a reference to
  * each struct page that each user address corresponds to at a given
@@ -770,14 +999,12 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
  * appropriate) must be called after the page is finished with, and
  * before put_page is called.
  *
- * If @nonblocking != NULL, __get_user_pages will not wait for disk IO
- * or mmap_sem contention, and if waiting is needed to pin all pages,
- * *@nonblocking will be set to 0.  Further, if @gup_flags does not
- * include FOLL_NOWAIT, the mmap_sem will be released via up_read() in
- * this case.
+ * If @locked != NULL, *@locked will be set to 0 when mmap_lock is
+ * released by an up_read().  That can happen if @gup_flags does not
+ * have FOLL_NOWAIT.
  *
- * A caller using such a combination of @nonblocking and @gup_flags
- * must therefore hold the mmap_sem for reading only, and recognize
+ * A caller using such a combination of @locked and @gup_flags
+ * must therefore hold the mmap_lock for reading only, and recognize
  * when it's been released.  Otherwise, it must be held for either
  * reading or writing and will not be released.
  *
@@ -785,10 +1012,10 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
  * instead of __get_user_pages. __get_user_pages should be used only if
  * you need some special @gup_flags.
  */
-static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+static long __get_user_pages(struct mm_struct *mm,
 		unsigned long start, unsigned long nr_pages,
 		unsigned int gup_flags, struct page **pages,
-		struct vm_area_struct **vmas, int *nonblocking)
+		struct vm_area_struct **vmas, int *locked)
 {
 	long ret = 0, i = 0;
 	struct vm_area_struct *vma = NULL;
@@ -799,7 +1026,7 @@ static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 
 	start = untagged_addr(start);
 
-	VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET));
+	VM_BUG_ON(!!pages != !!(gup_flags & (FOLL_GET | FOLL_PIN)));
 
 	/*
 	 * If FOLL_FORCE is set then do not force a full fault as the hinting
@@ -832,39 +1059,42 @@ static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 				goto out;
 			}
 			if (is_vm_hugetlb_page(vma)) {
-				if (should_force_cow_break(vma, foll_flags))
-					foll_flags |= FOLL_WRITE;
 				i = follow_hugetlb_page(mm, vma, pages, vmas,
 						&start, &nr_pages, i,
-						foll_flags, nonblocking);
+						gup_flags, locked);
+				if (locked && *locked == 0) {
+					/*
+					 * We've got a VM_FAULT_RETRY
+					 * and we've lost mmap_lock.
+					 * We must stop here.
+					 */
+					BUG_ON(gup_flags & FOLL_NOWAIT);
+					BUG_ON(ret != 0);
+					goto out;
+				}
 				continue;
 			}
 		}
-
-		if (should_force_cow_break(vma, foll_flags))
-			foll_flags |= FOLL_WRITE;
-
 retry:
 		/*
 		 * If we have a pending SIGKILL, don't keep faulting pages and
 		 * potentially allocating memory.
 		 */
 		if (fatal_signal_pending(current)) {
-			ret = -ERESTARTSYS;
+			ret = -EINTR;
 			goto out;
 		}
 		cond_resched();
 
 		page = follow_page_mask(vma, start, foll_flags, &ctx);
 		if (!page) {
-			ret = faultin_page(tsk, vma, start, &foll_flags,
-					nonblocking);
+			ret = faultin_page(vma, start, &foll_flags, locked);
 			switch (ret) {
 			case 0:
 				goto retry;
 			case -EBUSY:
 				ret = 0;
-				/* FALLTHRU */
+				fallthrough;
 			case -EFAULT:
 			case -ENOMEM:
 			case -EHWPOISON:
@@ -930,15 +1160,14 @@ static bool vma_permits_fault(struct vm_area_struct *vma,
 	return true;
 }
 
-/*
+/**
  * fixup_user_fault() - manually resolve a user page fault
- * @tsk:	the task_struct to use for page fault accounting, or
- *		NULL if faults are not to be recorded.
  * @mm:		mm_struct of target mm
  * @address:	user address
  * @fault_flags:flags to pass down to handle_mm_fault()
- * @unlocked:	did we unlock the mmap_sem while retrying, maybe NULL if caller
- *		does not allow retry
+ * @unlocked:	did we unlock the mmap_lock while retrying, maybe NULL if caller
+ *		does not allow retry. If NULL, the caller must guarantee
+ *		that fault_flags does not contain FAULT_FLAG_ALLOW_RETRY.
  *
  * This is meant to be called in the specific scenario where for locking reasons
  * we try to access user memory in atomic context (within a pagefault_disable()
@@ -957,10 +1186,10 @@ static bool vma_permits_fault(struct vm_area_struct *vma,
  * such architectures, gup() will not be enough to make a subsequent access
  * succeed.
  *
- * This function will not return with an unlocked mmap_sem. So it has not the
- * same semantics wrt the @mm->mmap_sem as does filemap_fault().
+ * This function will not return with an unlocked mmap_lock. So it has not the
+ * same semantics wrt the @mm->mmap_lock as does filemap_fault().
  */
-int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
+int fixup_user_fault(struct mm_struct *mm,
 		     unsigned long address, unsigned int fault_flags,
 		     bool *unlocked)
 {
@@ -970,7 +1199,7 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
 	address = untagged_addr(address);
 
 	if (unlocked)
-		fault_flags |= FAULT_FLAG_ALLOW_RETRY;
+		fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 retry:
 	vma = find_extend_vma(mm, address);
@@ -980,7 +1209,11 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
 	if (!vma_permits_fault(vma, fault_flags))
 		return -EFAULT;
 
-	ret = handle_mm_fault(vma, address, fault_flags);
+	if ((fault_flags & FAULT_FLAG_KILLABLE) &&
+	    fatal_signal_pending(current))
+		return -EINTR;
+
+	ret = handle_mm_fault(vma, address, fault_flags, NULL);
 	major |= ret & VM_FAULT_MAJOR;
 	if (ret & VM_FAULT_ERROR) {
 		int err = vm_fault_to_errno(ret, 0);
@@ -991,27 +1224,21 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
 	}
 
 	if (ret & VM_FAULT_RETRY) {
-		down_read(&mm->mmap_sem);
-		if (!(fault_flags & FAULT_FLAG_TRIED)) {
-			*unlocked = true;
-			fault_flags &= ~FAULT_FLAG_ALLOW_RETRY;
-			fault_flags |= FAULT_FLAG_TRIED;
-			goto retry;
-		}
+		mmap_read_lock(mm);
+		*unlocked = true;
+		fault_flags |= FAULT_FLAG_TRIED;
+		goto retry;
 	}
 
-	if (tsk) {
-		if (major)
-			tsk->maj_flt++;
-		else
-			tsk->min_flt++;
-	}
 	return 0;
 }
 EXPORT_SYMBOL_GPL(fixup_user_fault);
 
-static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
-						struct mm_struct *mm,
+/*
+ * Please note that this function, unlike __get_user_pages will not
+ * return 0 for nr_pages > 0 without FOLL_NOWAIT
+ */
+static __always_inline long __get_user_pages_locked(struct mm_struct *mm,
 						unsigned long start,
 						unsigned long nr_pages,
 						struct page **pages,
@@ -1029,13 +1256,25 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
 		BUG_ON(*locked != 1);
 	}
 
-	if (pages)
+	if (flags & FOLL_PIN)
+		atomic_set(&mm->has_pinned, 1);
+
+	/*
+	 * FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior
+	 * is to set FOLL_GET if the caller wants pages[] filled in (but has
+	 * carelessly failed to specify FOLL_GET), so keep doing that, but only
+	 * for FOLL_GET, not for the newer FOLL_PIN.
+	 *
+	 * FOLL_PIN always expects pages to be non-null, but no need to assert
+	 * that here, as any failures will be obvious enough.
+	 */
+	if (pages && !(flags & FOLL_PIN))
 		flags |= FOLL_GET;
 
 	pages_done = 0;
 	lock_dropped = false;
 	for (;;) {
-		ret = __get_user_pages(tsk, mm, start, nr_pages, flags, pages,
+		ret = __get_user_pages(mm, start, nr_pages, flags, pages,
 				       vmas, locked);
 		if (!locked)
 			/* VM_FAULT_RETRY couldn't trigger, bypass */
@@ -1069,17 +1308,39 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
 		if (likely(pages))
 			pages += ret;
 		start += ret << PAGE_SHIFT;
+		lock_dropped = true;
 
+retry:
 		/*
 		 * Repeat on the address that fired VM_FAULT_RETRY
-		 * without FAULT_FLAG_ALLOW_RETRY but with
-		 * FAULT_FLAG_TRIED.
+		 * with both FAULT_FLAG_ALLOW_RETRY and
+		 * FAULT_FLAG_TRIED.  Note that GUP can be interrupted
+		 * by fatal signals, so we need to check it before we
+		 * start trying again otherwise it can loop forever.
 		 */
+
+		if (fatal_signal_pending(current)) {
+			if (!pages_done)
+				pages_done = -EINTR;
+			break;
+		}
+
+		ret = mmap_read_lock_killable(mm);
+		if (ret) {
+			BUG_ON(ret > 0);
+			if (!pages_done)
+				pages_done = ret;
+			break;
+		}
+
 		*locked = 1;
-		lock_dropped = true;
-		down_read(&mm->mmap_sem);
-		ret = __get_user_pages(tsk, mm, start, 1, flags | FOLL_TRIED,
-				       pages, NULL, NULL);
+		ret = __get_user_pages(mm, start, 1, flags | FOLL_TRIED,
+				       pages, NULL, locked);
+		if (!*locked) {
+			/* Continue to retry until we succeeded */
+			BUG_ON(ret != 0);
+			goto retry;
+		}
 		if (ret != 1) {
 			BUG_ON(ret > 1);
 			if (!pages_done)
@@ -1099,109 +1360,34 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
 		 * We must let the caller know we temporarily dropped the lock
 		 * and so the critical section protected by it was lost.
 		 */
-		up_read(&mm->mmap_sem);
+		mmap_read_unlock(mm);
 		*locked = 0;
 	}
 	return pages_done;
 }
 
-/*
- * get_user_pages_remote() - pin user pages in memory
- * @tsk:	the task_struct to use for page fault accounting, or
- *		NULL if faults are not to be recorded.
- * @mm:		mm_struct of target mm
- * @start:	starting user address
- * @nr_pages:	number of pages from start to pin
- * @gup_flags:	flags modifying lookup behaviour
- * @pages:	array that receives pointers to the pages pinned.
- *		Should be at least nr_pages long. Or NULL, if caller
- *		only intends to ensure the pages are faulted in.
- * @vmas:	array of pointers to vmas corresponding to each page.
- *		Or NULL if the caller does not require them.
- * @locked:	pointer to lock flag indicating whether lock is held and
- *		subsequently whether VM_FAULT_RETRY functionality can be
- *		utilised. Lock must initially be held.
- *
- * Returns number of pages pinned. This may be fewer than the number
- * requested. If nr_pages is 0 or negative, returns 0. If no pages
- * were pinned, returns -errno. Each page returned must be released
- * with a put_page() call when it is finished with. vmas will only
- * remain valid while mmap_sem is held.
- *
- * Must be called with mmap_sem held for read or write.
- *
- * get_user_pages walks a process's page tables and takes a reference to
- * each struct page that each user address corresponds to at a given
- * instant. That is, it takes the page that would be accessed if a user
- * thread accesses the given user virtual address at that instant.
- *
- * This does not guarantee that the page exists in the user mappings when
- * get_user_pages returns, and there may even be a completely different
- * page there in some cases (eg. if mmapped pagecache has been invalidated
- * and subsequently re faulted). However it does guarantee that the page
- * won't be freed completely. And mostly callers simply care that the page
- * contains data that was valid *at some point in time*. Typically, an IO
- * or similar operation cannot guarantee anything stronger anyway because
- * locks can't be held over the syscall boundary.
- *
- * If gup_flags & FOLL_WRITE == 0, the page must not be written to. If the page
- * is written to, set_page_dirty (or set_page_dirty_lock, as appropriate) must
- * be called after the page is finished with, and before put_page is called.
- *
- * get_user_pages is typically used for fewer-copy IO operations, to get a
- * handle on the memory by some means other than accesses via the user virtual
- * addresses. The pages may be submitted for DMA to devices or accessed via
- * their kernel linear mapping (via the kmap APIs). Care should be taken to
- * use the correct cache flushing APIs.
- *
- * See also get_user_pages_fast, for performance critical applications.
- *
- * get_user_pages should be phased out in favor of
- * get_user_pages_locked|unlocked or get_user_pages_fast. Nothing
- * should use get_user_pages because it cannot pass
- * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault.
- */
-long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
-		unsigned long start, unsigned long nr_pages,
-		unsigned int gup_flags, struct page **pages,
-		struct vm_area_struct **vmas, int *locked)
-{
-	/*
-	 * FIXME: Current FOLL_LONGTERM behavior is incompatible with
-	 * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
-	 * vmas.  As there are no users of this flag in this call we simply
-	 * disallow this option for now.
-	 */
-	if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
-		return -EINVAL;
-
-	return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,
-				       locked,
-				       gup_flags | FOLL_TOUCH | FOLL_REMOTE);
-}
-EXPORT_SYMBOL(get_user_pages_remote);
-
 /**
  * populate_vma_page_range() -  populate a range of pages in the vma.
  * @vma:   target vma
  * @start: start address
  * @end:   end address
- * @nonblocking:
+ * @locked: whether the mmap_lock is still held
  *
  * This takes care of mlocking the pages too if VM_LOCKED is set.
  *
- * return 0 on success, negative error code on error.
+ * Return either number of pages pinned in the vma, or a negative error
+ * code on error.
  *
- * vma->vm_mm->mmap_sem must be held.
+ * vma->vm_mm->mmap_lock must be held.
  *
- * If @nonblocking is NULL, it may be held for read or write and will
+ * If @locked is NULL, it may be held for read or write and will
  * be unperturbed.
  *
- * If @nonblocking is non-NULL, it must held for read only and may be
- * released.  If it's released, *@nonblocking will be set to 0.
+ * If @locked is non-NULL, it must held for read only and may be
+ * released.  If it's released, *@locked will be set to 0.
  */
 long populate_vma_page_range(struct vm_area_struct *vma,
-		unsigned long start, unsigned long end, int *nonblocking)
+		unsigned long start, unsigned long end, int *locked)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long nr_pages = (end - start) / PAGE_SIZE;
@@ -1211,7 +1397,7 @@ long populate_vma_page_range(struct vm_area_struct *vma,
 	VM_BUG_ON(end   & ~PAGE_MASK);
 	VM_BUG_ON_VMA(start < vma->vm_start, vma);
 	VM_BUG_ON_VMA(end   > vma->vm_end, vma);
-	VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm);
+	mmap_assert_locked(mm);
 
 	gup_flags = FOLL_TOUCH | FOLL_POPULATE | FOLL_MLOCK;
 	if (vma->vm_flags & VM_LOCKONFAULT)
@@ -1228,15 +1414,15 @@ long populate_vma_page_range(struct vm_area_struct *vma,
 	 * We want mlock to succeed for regions that have any permissions
 	 * other than PROT_NONE.
 	 */
-	if (vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC))
+	if (vma_is_accessible(vma))
 		gup_flags |= FOLL_FORCE;
 
 	/*
 	 * We made sure addr is within a VMA, so the following will
 	 * not result in a stack expansion that recurses back here.
 	 */
-	return __get_user_pages(current, mm, start, nr_pages, gup_flags,
-				NULL, NULL, nonblocking);
+	return __get_user_pages(mm, start, nr_pages, gup_flags,
+				NULL, NULL, locked);
 }
 
 /*
@@ -1244,7 +1430,7 @@ long populate_vma_page_range(struct vm_area_struct *vma,
  *
  * This is used to implement mlock() and the MAP_POPULATE / MAP_LOCKED mmap
  * flags. VMAs must be already marked with the desired vm_flags, and
- * mmap_sem must not be held.
+ * mmap_lock must not be held.
  */
 int __mm_populate(unsigned long start, unsigned long len, int ignore_errors)
 {
@@ -1263,7 +1449,7 @@ int __mm_populate(unsigned long start, unsigned long len, int ignore_errors)
 		 */
 		if (!locked) {
 			locked = 1;
-			down_read(&mm->mmap_sem);
+			mmap_read_lock(mm);
 			vma = find_vma(mm, nstart);
 		} else if (nstart >= vma->vm_end)
 			vma = vma->vm_next;
@@ -1295,41 +1481,11 @@ int __mm_populate(unsigned long start, unsigned long len, int ignore_errors)
 		ret = 0;
 	}
 	if (locked)
-		up_read(&mm->mmap_sem);
+		mmap_read_unlock(mm);
 	return ret;	/* 0 or negative error code */
 }
-
-/**
- * get_dump_page() - pin user page in memory while writing it to core dump
- * @addr: user address
- *
- * Returns struct page pointer of user page pinned for dump,
- * to be freed afterwards by put_page().
- *
- * Returns NULL on any kind of failure - a hole must then be inserted into
- * the corefile, to preserve alignment with its headers; and also returns
- * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found -
- * allowing a hole to be left in the corefile to save diskspace.
- *
- * Called without mmap_sem, but after all other threads have been killed.
- */
-#ifdef CONFIG_ELF_CORE
-struct page *get_dump_page(unsigned long addr)
-{
-	struct vm_area_struct *vma;
-	struct page *page;
-
-	if (__get_user_pages(current, current->mm, addr, 1,
-			     FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma,
-			     NULL) < 1)
-		return NULL;
-	flush_cache_page(vma, addr, page_to_pfn(page));
-	return page;
-}
-#endif /* CONFIG_ELF_CORE */
 #else /* CONFIG_MMU */
-static long __get_user_pages_locked(struct task_struct *tsk,
-		struct mm_struct *mm, unsigned long start,
+static long __get_user_pages_locked(struct mm_struct *mm, unsigned long start,
 		unsigned long nr_pages, struct page **pages,
 		struct vm_area_struct **vmas, int *locked,
 		unsigned int foll_flags)
@@ -1373,6 +1529,38 @@ static long __get_user_pages_locked(struct task_struct *tsk,
 }
 #endif /* !CONFIG_MMU */
 
+/**
+ * get_dump_page() - pin user page in memory while writing it to core dump
+ * @addr: user address
+ *
+ * Returns struct page pointer of user page pinned for dump,
+ * to be freed afterwards by put_page().
+ *
+ * Returns NULL on any kind of failure - a hole must then be inserted into
+ * the corefile, to preserve alignment with its headers; and also returns
+ * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found -
+ * allowing a hole to be left in the corefile to save diskspace.
+ *
+ * Called without mmap_lock (takes and releases the mmap_lock by itself).
+ */
+#ifdef CONFIG_ELF_CORE
+struct page *get_dump_page(unsigned long addr)
+{
+	struct mm_struct *mm = current->mm;
+	struct page *page;
+	int locked = 1;
+	int ret;
+
+	if (mmap_read_lock_killable(mm))
+		return NULL;
+	ret = __get_user_pages_locked(mm, addr, 1, &page, NULL, &locked,
+				      FOLL_FORCE | FOLL_DUMP | FOLL_GET);
+	if (locked)
+		mmap_read_unlock(mm);
+	return (ret == 1) ? page : NULL;
+}
+#endif /* CONFIG_ELF_CORE */
+
 #if defined(CONFIG_FS_DAX) || defined (CONFIG_CMA)
 static bool check_dax_vmas(struct vm_area_struct **vmas, long nr_pages)
 {
@@ -1394,146 +1582,102 @@ static bool check_dax_vmas(struct vm_area_struct **vmas, long nr_pages)
 }
 
 #ifdef CONFIG_CMA
-static struct page *new_non_cma_page(struct page *page, unsigned long private)
-{
-	/*
-	 * We want to make sure we allocate the new page from the same node
-	 * as the source page.
-	 */
-	int nid = page_to_nid(page);
-	/*
-	 * Trying to allocate a page for migration. Ignore allocation
-	 * failure warnings. We don't force __GFP_THISNODE here because
-	 * this node here is the node where we have CMA reservation and
-	 * in some case these nodes will have really less non movable
-	 * allocation memory.
-	 */
-	gfp_t gfp_mask = GFP_USER | __GFP_NOWARN;
-
-	if (PageHighMem(page))
-		gfp_mask |= __GFP_HIGHMEM;
-
-#ifdef CONFIG_HUGETLB_PAGE
-	if (PageHuge(page)) {
-		struct hstate *h = page_hstate(page);
-		/*
-		 * We don't want to dequeue from the pool because pool pages will
-		 * mostly be from the CMA region.
-		 */
-		return alloc_migrate_huge_page(h, gfp_mask, nid, NULL);
-	}
-#endif
-	if (PageTransHuge(page)) {
-		struct page *thp;
-		/*
-		 * ignore allocation failure warnings
-		 */
-		gfp_t thp_gfpmask = GFP_TRANSHUGE | __GFP_NOWARN;
-
-		/*
-		 * Remove the movable mask so that we don't allocate from
-		 * CMA area again.
-		 */
-		thp_gfpmask &= ~__GFP_MOVABLE;
-		thp = __alloc_pages_node(nid, thp_gfpmask, HPAGE_PMD_ORDER);
-		if (!thp)
-			return NULL;
-		prep_transhuge_page(thp);
-		return thp;
-	}
-
-	return __alloc_pages_node(nid, gfp_mask, 0);
-}
-
-static long check_and_migrate_cma_pages(struct task_struct *tsk,
-					struct mm_struct *mm,
+static long check_and_migrate_cma_pages(struct mm_struct *mm,
 					unsigned long start,
 					unsigned long nr_pages,
 					struct page **pages,
 					struct vm_area_struct **vmas,
 					unsigned int gup_flags)
 {
-	unsigned long i;
-	unsigned long step;
-	bool drain_allow = true;
-	bool migrate_allow = true;
+	unsigned long i, isolation_error_count;
+	bool drain_allow;
 	LIST_HEAD(cma_page_list);
+	long ret = nr_pages;
+	struct page *prev_head, *head;
+	struct migration_target_control mtc = {
+		.nid = NUMA_NO_NODE,
+		.gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_NOWARN,
+	};
 
 check_again:
-	for (i = 0; i < nr_pages;) {
-
-		struct page *head = compound_head(pages[i]);
-
-		/*
-		 * gup may start from a tail page. Advance step by the left
-		 * part.
-		 */
-		step = compound_nr(head) - (pages[i] - head);
+	prev_head = NULL;
+	isolation_error_count = 0;
+	drain_allow = true;
+	for (i = 0; i < nr_pages; i++) {
+		head = compound_head(pages[i]);
+		if (head == prev_head)
+			continue;
+		prev_head = head;
 		/*
 		 * If we get a page from the CMA zone, since we are going to
 		 * be pinning these entries, we might as well move them out
 		 * of the CMA zone if possible.
 		 */
 		if (is_migrate_cma_page(head)) {
-			if (PageHuge(head))
-				isolate_huge_page(head, &cma_page_list);
-			else {
+			if (PageHuge(head)) {
+				if (!isolate_huge_page(head, &cma_page_list))
+					isolation_error_count++;
+			} else {
 				if (!PageLRU(head) && drain_allow) {
 					lru_add_drain_all();
 					drain_allow = false;
 				}
 
-				if (!isolate_lru_page(head)) {
-					list_add_tail(&head->lru, &cma_page_list);
-					mod_node_page_state(page_pgdat(head),
-							    NR_ISOLATED_ANON +
-							    page_is_file_cache(head),
-							    hpage_nr_pages(head));
+				if (isolate_lru_page(head)) {
+					isolation_error_count++;
+					continue;
 				}
+				list_add_tail(&head->lru, &cma_page_list);
+				mod_node_page_state(page_pgdat(head),
+						    NR_ISOLATED_ANON +
+						    page_is_file_lru(head),
+						    thp_nr_pages(head));
 			}
 		}
-
-		i += step;
 	}
 
+	/*
+	 * If list is empty, and no isolation errors, means that all pages are
+	 * in the correct zone.
+	 */
+	if (list_empty(&cma_page_list) && !isolation_error_count)
+		return ret;
+
 	if (!list_empty(&cma_page_list)) {
 		/*
 		 * drop the above get_user_pages reference.
 		 */
-		for (i = 0; i < nr_pages; i++)
-			put_page(pages[i]);
+		if (gup_flags & FOLL_PIN)
+			unpin_user_pages(pages, nr_pages);
+		else
+			for (i = 0; i < nr_pages; i++)
+				put_page(pages[i]);
 
-		if (migrate_pages(&cma_page_list, new_non_cma_page,
-				  NULL, 0, MIGRATE_SYNC, MR_CONTIG_RANGE)) {
-			/*
-			 * some of the pages failed migration. Do get_user_pages
-			 * without migration.
-			 */
-			migrate_allow = false;
-
+		ret = migrate_pages(&cma_page_list, alloc_migration_target,
+				    NULL, (unsigned long)&mtc, MIGRATE_SYNC,
+				    MR_CONTIG_RANGE);
+		if (ret) {
 			if (!list_empty(&cma_page_list))
 				putback_movable_pages(&cma_page_list);
+			return ret > 0 ? -ENOMEM : ret;
 		}
-		/*
-		 * We did migrate all the pages, Try to get the page references
-		 * again migrating any new CMA pages which we failed to isolate
-		 * earlier.
-		 */
-		nr_pages = __get_user_pages_locked(tsk, mm, start, nr_pages,
-						   pages, vmas, NULL,
-						   gup_flags);
 
-		if ((nr_pages > 0) && migrate_allow) {
-			drain_allow = true;
-			goto check_again;
-		}
+		/* We unpinned pages before migration, pin them again */
+		ret = __get_user_pages_locked(mm, start, nr_pages, pages, vmas,
+					      NULL, gup_flags);
+		if (ret <= 0)
+			return ret;
+		nr_pages = ret;
 	}
 
-	return nr_pages;
+	/*
+	 * check again because pages were unpinned, and we also might have
+	 * had isolation errors and need more pages to migrate.
+	 */
+	goto check_again;
 }
 #else
-static long check_and_migrate_cma_pages(struct task_struct *tsk,
-					struct mm_struct *mm,
+static long check_and_migrate_cma_pages(struct mm_struct *mm,
 					unsigned long start,
 					unsigned long nr_pages,
 					struct page **pages,
@@ -1548,8 +1692,7 @@ static long check_and_migrate_cma_pages(struct task_struct *tsk,
  * __gup_longterm_locked() is a wrapper for __get_user_pages_locked which
  * allows us to process the FOLL_LONGTERM flag.
  */
-static long __gup_longterm_locked(struct task_struct *tsk,
-				  struct mm_struct *mm,
+static long __gup_longterm_locked(struct mm_struct *mm,
 				  unsigned long start,
 				  unsigned long nr_pages,
 				  struct page **pages,
@@ -1574,80 +1717,245 @@ static long __gup_longterm_locked(struct task_struct *tsk,
 		flags = memalloc_nocma_save();
 	}
 
-	rc = __get_user_pages_locked(tsk, mm, start, nr_pages, pages,
+	rc = __get_user_pages_locked(mm, start, nr_pages, pages,
 				     vmas_tmp, NULL, gup_flags);
 
 	if (gup_flags & FOLL_LONGTERM) {
-		memalloc_nocma_restore(flags);
 		if (rc < 0)
 			goto out;
 
 		if (check_dax_vmas(vmas_tmp, rc)) {
-			for (i = 0; i < rc; i++)
-				put_page(pages[i]);
+			if (gup_flags & FOLL_PIN)
+				unpin_user_pages(pages, rc);
+			else
+				for (i = 0; i < rc; i++)
+					put_page(pages[i]);
 			rc = -EOPNOTSUPP;
 			goto out;
 		}
 
-		rc = check_and_migrate_cma_pages(tsk, mm, start, rc, pages,
+		rc = check_and_migrate_cma_pages(mm, start, rc, pages,
 						 vmas_tmp, gup_flags);
+out:
+		memalloc_nocma_restore(flags);
 	}
 
-out:
 	if (vmas_tmp != vmas)
 		kfree(vmas_tmp);
 	return rc;
 }
 #else /* !CONFIG_FS_DAX && !CONFIG_CMA */
-static __always_inline long __gup_longterm_locked(struct task_struct *tsk,
-						  struct mm_struct *mm,
+static __always_inline long __gup_longterm_locked(struct mm_struct *mm,
 						  unsigned long start,
 						  unsigned long nr_pages,
 						  struct page **pages,
 						  struct vm_area_struct **vmas,
 						  unsigned int flags)
 {
-	return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,
+	return __get_user_pages_locked(mm, start, nr_pages, pages, vmas,
 				       NULL, flags);
 }
 #endif /* CONFIG_FS_DAX || CONFIG_CMA */
 
-/*
- * This is the same as get_user_pages_remote(), just with a
- * less-flexible calling convention where we assume that the task
- * and mm being operated on are the current task's and don't allow
- * passing of a locked parameter.  We also obviously don't pass
- * FOLL_REMOTE in here.
+static bool is_valid_gup_flags(unsigned int gup_flags)
+{
+	/*
+	 * FOLL_PIN must only be set internally by the pin_user_pages*() APIs,
+	 * never directly by the caller, so enforce that with an assertion:
+	 */
+	if (WARN_ON_ONCE(gup_flags & FOLL_PIN))
+		return false;
+	/*
+	 * FOLL_PIN is a prerequisite to FOLL_LONGTERM. Another way of saying
+	 * that is, FOLL_LONGTERM is a specific case, more restrictive case of
+	 * FOLL_PIN.
+	 */
+	if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
+		return false;
+
+	return true;
+}
+
+#ifdef CONFIG_MMU
+static long __get_user_pages_remote(struct mm_struct *mm,
+				    unsigned long start, unsigned long nr_pages,
+				    unsigned int gup_flags, struct page **pages,
+				    struct vm_area_struct **vmas, int *locked)
+{
+	/*
+	 * Parts of FOLL_LONGTERM behavior are incompatible with
+	 * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
+	 * vmas. However, this only comes up if locked is set, and there are
+	 * callers that do request FOLL_LONGTERM, but do not set locked. So,
+	 * allow what we can.
+	 */
+	if (gup_flags & FOLL_LONGTERM) {
+		if (WARN_ON_ONCE(locked))
+			return -EINVAL;
+		/*
+		 * This will check the vmas (even if our vmas arg is NULL)
+		 * and return -ENOTSUPP if DAX isn't allowed in this case:
+		 */
+		return __gup_longterm_locked(mm, start, nr_pages, pages,
+					     vmas, gup_flags | FOLL_TOUCH |
+					     FOLL_REMOTE);
+	}
+
+	return __get_user_pages_locked(mm, start, nr_pages, pages, vmas,
+				       locked,
+				       gup_flags | FOLL_TOUCH | FOLL_REMOTE);
+}
+
+/**
+ * get_user_pages_remote() - pin user pages in memory
+ * @mm:		mm_struct of target mm
+ * @start:	starting user address
+ * @nr_pages:	number of pages from start to pin
+ * @gup_flags:	flags modifying lookup behaviour
+ * @pages:	array that receives pointers to the pages pinned.
+ *		Should be at least nr_pages long. Or NULL, if caller
+ *		only intends to ensure the pages are faulted in.
+ * @vmas:	array of pointers to vmas corresponding to each page.
+ *		Or NULL if the caller does not require them.
+ * @locked:	pointer to lock flag indicating whether lock is held and
+ *		subsequently whether VM_FAULT_RETRY functionality can be
+ *		utilised. Lock must initially be held.
+ *
+ * Returns either number of pages pinned (which may be less than the
+ * number requested), or an error. Details about the return value:
+ *
+ * -- If nr_pages is 0, returns 0.
+ * -- If nr_pages is >0, but no pages were pinned, returns -errno.
+ * -- If nr_pages is >0, and some pages were pinned, returns the number of
+ *    pages pinned. Again, this may be less than nr_pages.
+ *
+ * The caller is responsible for releasing returned @pages, via put_page().
+ *
+ * @vmas are valid only as long as mmap_lock is held.
+ *
+ * Must be called with mmap_lock held for read or write.
+ *
+ * get_user_pages_remote walks a process's page tables and takes a reference
+ * to each struct page that each user address corresponds to at a given
+ * instant. That is, it takes the page that would be accessed if a user
+ * thread accesses the given user virtual address at that instant.
+ *
+ * This does not guarantee that the page exists in the user mappings when
+ * get_user_pages_remote returns, and there may even be a completely different
+ * page there in some cases (eg. if mmapped pagecache has been invalidated
+ * and subsequently re faulted). However it does guarantee that the page
+ * won't be freed completely. And mostly callers simply care that the page
+ * contains data that was valid *at some point in time*. Typically, an IO
+ * or similar operation cannot guarantee anything stronger anyway because
+ * locks can't be held over the syscall boundary.
+ *
+ * If gup_flags & FOLL_WRITE == 0, the page must not be written to. If the page
+ * is written to, set_page_dirty (or set_page_dirty_lock, as appropriate) must
+ * be called after the page is finished with, and before put_page is called.
+ *
+ * get_user_pages_remote is typically used for fewer-copy IO operations,
+ * to get a handle on the memory by some means other than accesses
+ * via the user virtual addresses. The pages may be submitted for
+ * DMA to devices or accessed via their kernel linear mapping (via the
+ * kmap APIs). Care should be taken to use the correct cache flushing APIs.
+ *
+ * See also get_user_pages_fast, for performance critical applications.
+ *
+ * get_user_pages_remote should be phased out in favor of
+ * get_user_pages_locked|unlocked or get_user_pages_fast. Nothing
+ * should use get_user_pages_remote because it cannot pass
+ * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault.
+ */
+long get_user_pages_remote(struct mm_struct *mm,
+		unsigned long start, unsigned long nr_pages,
+		unsigned int gup_flags, struct page **pages,
+		struct vm_area_struct **vmas, int *locked)
+{
+	if (!is_valid_gup_flags(gup_flags))
+		return -EINVAL;
+
+	return __get_user_pages_remote(mm, start, nr_pages, gup_flags,
+				       pages, vmas, locked);
+}
+EXPORT_SYMBOL(get_user_pages_remote);
+
+#else /* CONFIG_MMU */
+long get_user_pages_remote(struct mm_struct *mm,
+			   unsigned long start, unsigned long nr_pages,
+			   unsigned int gup_flags, struct page **pages,
+			   struct vm_area_struct **vmas, int *locked)
+{
+	return 0;
+}
+
+static long __get_user_pages_remote(struct mm_struct *mm,
+				    unsigned long start, unsigned long nr_pages,
+				    unsigned int gup_flags, struct page **pages,
+				    struct vm_area_struct **vmas, int *locked)
+{
+	return 0;
+}
+#endif /* !CONFIG_MMU */
+
+/**
+ * get_user_pages() - pin user pages in memory
+ * @start:      starting user address
+ * @nr_pages:   number of pages from start to pin
+ * @gup_flags:  flags modifying lookup behaviour
+ * @pages:      array that receives pointers to the pages pinned.
+ *              Should be at least nr_pages long. Or NULL, if caller
+ *              only intends to ensure the pages are faulted in.
+ * @vmas:       array of pointers to vmas corresponding to each page.
+ *              Or NULL if the caller does not require them.
+ *
+ * This is the same as get_user_pages_remote(), just with a less-flexible
+ * calling convention where we assume that the mm being operated on belongs to
+ * the current task, and doesn't allow passing of a locked parameter.  We also
+ * obviously don't pass FOLL_REMOTE in here.
  */
 long get_user_pages(unsigned long start, unsigned long nr_pages,
 		unsigned int gup_flags, struct page **pages,
 		struct vm_area_struct **vmas)
 {
-	return __gup_longterm_locked(current, current->mm, start, nr_pages,
+	if (!is_valid_gup_flags(gup_flags))
+		return -EINVAL;
+
+	return __gup_longterm_locked(current->mm, start, nr_pages,
 				     pages, vmas, gup_flags | FOLL_TOUCH);
 }
 EXPORT_SYMBOL(get_user_pages);
 
-/*
- * We can leverage the VM_FAULT_RETRY functionality in the page fault
- * paths better by using either get_user_pages_locked() or
- * get_user_pages_unlocked().
- *
+/**
  * get_user_pages_locked() is suitable to replace the form:
  *
- *      down_read(&mm->mmap_sem);
+ *      mmap_read_lock(mm);
  *      do_something()
- *      get_user_pages(tsk, mm, ..., pages, NULL);
- *      up_read(&mm->mmap_sem);
+ *      get_user_pages(mm, ..., pages, NULL);
+ *      mmap_read_unlock(mm);
  *
  *  to:
  *
  *      int locked = 1;
- *      down_read(&mm->mmap_sem);
+ *      mmap_read_lock(mm);
  *      do_something()
- *      get_user_pages_locked(tsk, mm, ..., pages, &locked);
+ *      get_user_pages_locked(mm, ..., pages, &locked);
  *      if (locked)
- *          up_read(&mm->mmap_sem);
+ *          mmap_read_unlock(mm);
+ *
+ * @start:      starting user address
+ * @nr_pages:   number of pages from start to pin
+ * @gup_flags:  flags modifying lookup behaviour
+ * @pages:      array that receives pointers to the pages pinned.
+ *              Should be at least nr_pages long. Or NULL, if caller
+ *              only intends to ensure the pages are faulted in.
+ * @locked:     pointer to lock flag indicating whether lock is held and
+ *              subsequently whether VM_FAULT_RETRY functionality can be
+ *              utilised. Lock must initially be held.
+ *
+ * We can leverage the VM_FAULT_RETRY functionality in the page fault
+ * paths better by using either get_user_pages_locked() or
+ * get_user_pages_unlocked().
+ *
  */
 long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
 			   unsigned int gup_flags, struct page **pages,
@@ -1661,8 +1969,14 @@ long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
 	 */
 	if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
 		return -EINVAL;
+	/*
+	 * FOLL_PIN must only be set internally by the pin_user_pages*() APIs,
+	 * never directly by the caller, so enforce that:
+	 */
+	if (WARN_ON_ONCE(gup_flags & FOLL_PIN))
+		return -EINVAL;
 
-	return __get_user_pages_locked(current, current->mm, start, nr_pages,
+	return __get_user_pages_locked(current->mm, start, nr_pages,
 				       pages, NULL, locked,
 				       gup_flags | FOLL_TOUCH);
 }
@@ -1671,13 +1985,13 @@ EXPORT_SYMBOL(get_user_pages_locked);
 /*
  * get_user_pages_unlocked() is suitable to replace the form:
  *
- *      down_read(&mm->mmap_sem);
- *      get_user_pages(tsk, mm, ..., pages, NULL);
- *      up_read(&mm->mmap_sem);
+ *      mmap_read_lock(mm);
+ *      get_user_pages(mm, ..., pages, NULL);
+ *      mmap_read_unlock(mm);
  *
  *  with:
  *
- *      get_user_pages_unlocked(tsk, mm, ..., pages);
+ *      get_user_pages_unlocked(mm, ..., pages);
  *
  * It is functionally equivalent to get_user_pages_fast so
  * get_user_pages_fast should be used instead if specific gup_flags
@@ -1699,11 +2013,11 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
 	if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
 		return -EINVAL;
 
-	down_read(&mm->mmap_sem);
-	ret = __get_user_pages_locked(current, mm, start, nr_pages, pages, NULL,
+	mmap_read_lock(mm);
+	ret = __get_user_pages_locked(mm, start, nr_pages, pages, NULL,
 				      &locked, gup_flags | FOLL_TOUCH);
 	if (locked)
-		up_read(&mm->mmap_sem);
+		mmap_read_unlock(mm);
 	return ret;
 }
 EXPORT_SYMBOL(get_user_pages_unlocked);
@@ -1730,7 +2044,7 @@ EXPORT_SYMBOL(get_user_pages_unlocked);
  * Before activating this code, please be aware that the following assumptions
  * are currently made:
  *
- *  *) Either HAVE_RCU_TABLE_FREE is enabled, and tlb_remove_table() is used to
+ *  *) Either MMU_GATHER_RCU_TABLE_FREE is enabled, and tlb_remove_table() is used to
  *  free pages containing page tables or TLB flushing requires IPI broadcast.
  *
  *  *) ptes can be read atomically by the architecture.
@@ -1743,6 +2057,7 @@ EXPORT_SYMBOL(get_user_pages_unlocked);
  */
 #ifdef CONFIG_HAVE_FAST_GUP
 #ifdef CONFIG_GUP_GET_PTE_LOW_HIGH
+
 /*
  * WARNING: only to be used in the get_user_pages_fast() implementation.
  *
@@ -1793,35 +2108,25 @@ static inline pte_t gup_get_pte(pte_t *ptep)
  */
 static inline pte_t gup_get_pte(pte_t *ptep)
 {
-	return READ_ONCE(*ptep);
+	return ptep_get(ptep);
 }
 #endif /* CONFIG_GUP_GET_PTE_LOW_HIGH */
 
 static void __maybe_unused undo_dev_pagemap(int *nr, int nr_start,
+					    unsigned int flags,
 					    struct page **pages)
 {
 	while ((*nr) - nr_start) {
 		struct page *page = pages[--(*nr)];
 
 		ClearPageReferenced(page);
-		put_page(page);
+		if (flags & FOLL_PIN)
+			unpin_user_page(page);
+		else
+			put_page(page);
 	}
 }
 
-/*
- * Return the compund head page with ref appropriately incremented,
- * or NULL if that failed.
- */
-static inline struct page *try_get_compound_head(struct page *page, int refs)
-{
-	struct page *head = compound_head(page);
-	if (WARN_ON_ONCE(page_ref_count(head) < 0))
-		return NULL;
-	if (unlikely(!page_cache_add_speculative(head, refs)))
-		return NULL;
-	return head;
-}
-
 #ifdef CONFIG_ARCH_HAS_PTE_SPECIAL
 static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 			 unsigned int flags, struct page **pages, int *nr)
@@ -1851,7 +2156,7 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 
 			pgmap = get_dev_pagemap(pte_pfn(pte), pgmap);
 			if (unlikely(!pgmap)) {
-				undo_dev_pagemap(nr, nr_start, pages);
+				undo_dev_pagemap(nr, nr_start, flags, pages);
 				goto pte_unmap;
 			}
 		} else if (pte_special(pte))
@@ -1860,17 +2165,30 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
 		page = pte_page(pte);
 
-		head = try_get_compound_head(page, 1);
+		head = try_grab_compound_head(page, 1, flags);
 		if (!head)
 			goto pte_unmap;
 
 		if (unlikely(pte_val(pte) != pte_val(*ptep))) {
-			put_page(head);
+			put_compound_head(head, 1, flags);
 			goto pte_unmap;
 		}
 
 		VM_BUG_ON_PAGE(compound_head(page) != head, page);
 
+		/*
+		 * We need to make the page accessible if and only if we are
+		 * going to access its content (the FOLL_PIN case).  Please
+		 * see Documentation/core-api/pin_user_pages.rst for
+		 * details.
+		 */
+		if (flags & FOLL_PIN) {
+			ret = arch_make_page_accessible(page);
+			if (ret) {
+				unpin_user_page(page);
+				goto pte_unmap;
+			}
+		}
 		SetPageReferenced(page);
 		pages[*nr] = page;
 		(*nr)++;
@@ -1893,7 +2211,7 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
  * to be special.
  *
  * For a futex to be placed on a THP tail page, get_futex_key requires a
- * __get_user_pages_fast implementation that can pin pages. Thus it's still
+ * get_user_pages_fast_only implementation that can pin pages. Thus it's still
  * useful to have gup_huge_pmd even if we can't operate on ptes.
  */
 static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
@@ -1905,7 +2223,8 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 
 #if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
 static int __gup_device_huge(unsigned long pfn, unsigned long addr,
-		unsigned long end, struct page **pages, int *nr)
+			     unsigned long end, unsigned int flags,
+			     struct page **pages, int *nr)
 {
 	int nr_start = *nr;
 	struct dev_pagemap *pgmap = NULL;
@@ -1915,12 +2234,15 @@ static int __gup_device_huge(unsigned long pfn, unsigned long addr,
 
 		pgmap = get_dev_pagemap(pfn, pgmap);
 		if (unlikely(!pgmap)) {
-			undo_dev_pagemap(nr, nr_start, pages);
+			undo_dev_pagemap(nr, nr_start, flags, pages);
 			return 0;
 		}
 		SetPageReferenced(page);
 		pages[*nr] = page;
-		get_page(page);
+		if (unlikely(!try_grab_page(page, flags))) {
+			undo_dev_pagemap(nr, nr_start, flags, pages);
+			return 0;
+		}
 		(*nr)++;
 		pfn++;
 	} while (addr += PAGE_SIZE, addr != end);
@@ -1931,54 +2253,69 @@ static int __gup_device_huge(unsigned long pfn, unsigned long addr,
 }
 
 static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
-		unsigned long end, struct page **pages, int *nr)
+				 unsigned long end, unsigned int flags,
+				 struct page **pages, int *nr)
 {
 	unsigned long fault_pfn;
 	int nr_start = *nr;
 
 	fault_pfn = pmd_pfn(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
-	if (!__gup_device_huge(fault_pfn, addr, end, pages, nr))
+	if (!__gup_device_huge(fault_pfn, addr, end, flags, pages, nr))
 		return 0;
 
 	if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
-		undo_dev_pagemap(nr, nr_start, pages);
+		undo_dev_pagemap(nr, nr_start, flags, pages);
 		return 0;
 	}
 	return 1;
 }
 
 static int __gup_device_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
-		unsigned long end, struct page **pages, int *nr)
+				 unsigned long end, unsigned int flags,
+				 struct page **pages, int *nr)
 {
 	unsigned long fault_pfn;
 	int nr_start = *nr;
 
 	fault_pfn = pud_pfn(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
-	if (!__gup_device_huge(fault_pfn, addr, end, pages, nr))
+	if (!__gup_device_huge(fault_pfn, addr, end, flags, pages, nr))
 		return 0;
 
 	if (unlikely(pud_val(orig) != pud_val(*pudp))) {
-		undo_dev_pagemap(nr, nr_start, pages);
+		undo_dev_pagemap(nr, nr_start, flags, pages);
 		return 0;
 	}
 	return 1;
 }
 #else
 static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
-		unsigned long end, struct page **pages, int *nr)
+				 unsigned long end, unsigned int flags,
+				 struct page **pages, int *nr)
 {
 	BUILD_BUG();
 	return 0;
 }
 
 static int __gup_device_huge_pud(pud_t pud, pud_t *pudp, unsigned long addr,
-		unsigned long end, struct page **pages, int *nr)
+				 unsigned long end, unsigned int flags,
+				 struct page **pages, int *nr)
 {
 	BUILD_BUG();
 	return 0;
 }
 #endif
 
+static int record_subpages(struct page *page, unsigned long addr,
+			   unsigned long end, struct page **pages)
+{
+	int nr;
+
+	for (nr = 0; addr != end; addr += PAGE_SIZE)
+		pages[nr++] = page++;
+
+	return nr;
+}
+
 #ifdef CONFIG_ARCH_HAS_HUGEPD
 static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
 				      unsigned long sz)
@@ -2000,7 +2337,7 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
 	if (pte_end < end)
 		end = pte_end;
 
-	pte = READ_ONCE(*ptep);
+	pte = huge_ptep_get(ptep);
 
 	if (!pte_access_permitted(pte, flags & FOLL_WRITE))
 		return 0;
@@ -2008,32 +2345,20 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
 	/* hugepages are never "special" */
 	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
 
-	refs = 0;
 	head = pte_page(pte);
-
 	page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
-	do {
-		VM_BUG_ON(compound_head(page) != head);
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
+	refs = record_subpages(page, addr, end, pages + *nr);
 
-	head = try_get_compound_head(head, refs);
-	if (!head) {
-		*nr -= refs;
+	head = try_grab_compound_head(head, refs, flags);
+	if (!head)
 		return 0;
-	}
 
 	if (unlikely(pte_val(pte) != pte_val(*ptep))) {
-		/* Could be optimized better */
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
+		put_compound_head(head, refs, flags);
 		return 0;
 	}
 
+	*nr += refs;
 	SetPageReferenced(head);
 	return 1;
 }
@@ -2077,37 +2402,30 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 	if (pmd_devmap(orig)) {
 		if (unlikely(flags & FOLL_LONGTERM))
 			return 0;
-		return __gup_device_huge_pmd(orig, pmdp, addr, end, pages, nr);
+		return __gup_device_huge_pmd(orig, pmdp, addr, end, flags,
+					     pages, nr);
 	}
 
-	refs = 0;
 	page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
-	do {
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
+	refs = record_subpages(page, addr, end, pages + *nr);
 
-	head = try_get_compound_head(pmd_page(orig), refs);
-	if (!head) {
-		*nr -= refs;
+	head = try_grab_compound_head(pmd_page(orig), refs, flags);
+	if (!head)
 		return 0;
-	}
 
 	if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
+		put_compound_head(head, refs, flags);
 		return 0;
 	}
 
+	*nr += refs;
 	SetPageReferenced(head);
 	return 1;
 }
 
 static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
-		unsigned long end, unsigned int flags, struct page **pages, int *nr)
+			unsigned long end, unsigned int flags,
+			struct page **pages, int *nr)
 {
 	struct page *head, *page;
 	int refs;
@@ -2118,31 +2436,23 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 	if (pud_devmap(orig)) {
 		if (unlikely(flags & FOLL_LONGTERM))
 			return 0;
-		return __gup_device_huge_pud(orig, pudp, addr, end, pages, nr);
+		return __gup_device_huge_pud(orig, pudp, addr, end, flags,
+					     pages, nr);
 	}
 
-	refs = 0;
 	page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
-	do {
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
+	refs = record_subpages(page, addr, end, pages + *nr);
 
-	head = try_get_compound_head(pud_page(orig), refs);
-	if (!head) {
-		*nr -= refs;
+	head = try_grab_compound_head(pud_page(orig), refs, flags);
+	if (!head)
 		return 0;
-	}
 
 	if (unlikely(pud_val(orig) != pud_val(*pudp))) {
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
+		put_compound_head(head, refs, flags);
 		return 0;
 	}
 
+	*nr += refs;
 	SetPageReferenced(head);
 	return 1;
 }
@@ -2158,28 +2468,20 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
 		return 0;
 
 	BUILD_BUG_ON(pgd_devmap(orig));
-	refs = 0;
-	page = pgd_page(orig) + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);
-	do {
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
 
-	head = try_get_compound_head(pgd_page(orig), refs);
-	if (!head) {
-		*nr -= refs;
+	page = pgd_page(orig) + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);
+	refs = record_subpages(page, addr, end, pages + *nr);
+
+	head = try_grab_compound_head(pgd_page(orig), refs, flags);
+	if (!head)
 		return 0;
-	}
 
 	if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) {
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
+		put_compound_head(head, refs, flags);
 		return 0;
 	}
 
+	*nr += refs;
 	SetPageReferenced(head);
 	return 1;
 }
@@ -2238,7 +2540,7 @@ static int gup_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, unsigned lo
 		pud_t pud = READ_ONCE(*pudp);
 
 		next = pud_addr_end(addr, end);
-		if (pud_none(pud))
+		if (unlikely(!pud_present(pud)))
 			return 0;
 		if (unlikely(pud_huge(pud))) {
 			if (!gup_huge_pud(pud, pudp, addr, next, flags,
@@ -2314,7 +2616,7 @@ static inline void gup_pgd_range(unsigned long addr, unsigned long end,
 
 #ifndef gup_fast_permitted
 /*
- * Check if it's allowed to use __get_user_pages_fast() for the range, or
+ * Check if it's allowed to use get_user_pages_fast_only() for the range, or
  * we need to fall back to the slow version:
  */
 static bool gup_fast_permitted(unsigned long start, unsigned long end)
@@ -2323,7 +2625,132 @@ static bool gup_fast_permitted(unsigned long start, unsigned long end)
 }
 #endif
 
-/*
+static int __gup_longterm_unlocked(unsigned long start, int nr_pages,
+				   unsigned int gup_flags, struct page **pages)
+{
+	int ret;
+
+	/*
+	 * FIXME: FOLL_LONGTERM does not work with
+	 * get_user_pages_unlocked() (see comments in that function)
+	 */
+	if (gup_flags & FOLL_LONGTERM) {
+		mmap_read_lock(current->mm);
+		ret = __gup_longterm_locked(current->mm,
+					    start, nr_pages,
+					    pages, NULL, gup_flags);
+		mmap_read_unlock(current->mm);
+	} else {
+		ret = get_user_pages_unlocked(start, nr_pages,
+					      pages, gup_flags);
+	}
+
+	return ret;
+}
+
+static unsigned long lockless_pages_from_mm(unsigned long start,
+					    unsigned long end,
+					    unsigned int gup_flags,
+					    struct page **pages)
+{
+	unsigned long flags;
+	int nr_pinned = 0;
+	unsigned seq;
+
+	if (!IS_ENABLED(CONFIG_HAVE_FAST_GUP) ||
+	    !gup_fast_permitted(start, end))
+		return 0;
+
+	if (gup_flags & FOLL_PIN) {
+		seq = raw_read_seqcount(&current->mm->write_protect_seq);
+		if (seq & 1)
+			return 0;
+	}
+
+	/*
+	 * Disable interrupts. The nested form is used, in order to allow full,
+	 * general purpose use of this routine.
+	 *
+	 * With interrupts disabled, we block page table pages from being freed
+	 * from under us. See struct mmu_table_batch comments in
+	 * include/asm-generic/tlb.h for more details.
+	 *
+	 * We do not adopt an rcu_read_lock() here as we also want to block IPIs
+	 * that come from THPs splitting.
+	 */
+	local_irq_save(flags);
+	gup_pgd_range(start, end, gup_flags, pages, &nr_pinned);
+	local_irq_restore(flags);
+
+	/*
+	 * When pinning pages for DMA there could be a concurrent write protect
+	 * from fork() via copy_page_range(), in this case always fail fast GUP.
+	 */
+	if (gup_flags & FOLL_PIN) {
+		if (read_seqcount_retry(&current->mm->write_protect_seq, seq)) {
+			unpin_user_pages(pages, nr_pinned);
+			return 0;
+		}
+	}
+	return nr_pinned;
+}
+
+static int internal_get_user_pages_fast(unsigned long start,
+					unsigned long nr_pages,
+					unsigned int gup_flags,
+					struct page **pages)
+{
+	unsigned long len, end;
+	unsigned long nr_pinned;
+	int ret;
+
+	if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM |
+				       FOLL_FORCE | FOLL_PIN | FOLL_GET |
+				       FOLL_FAST_ONLY)))
+		return -EINVAL;
+
+	if (gup_flags & FOLL_PIN)
+		atomic_set(&current->mm->has_pinned, 1);
+
+	if (!(gup_flags & FOLL_FAST_ONLY))
+		might_lock_read(&current->mm->mmap_lock);
+
+	start = untagged_addr(start) & PAGE_MASK;
+	len = nr_pages << PAGE_SHIFT;
+	if (check_add_overflow(start, len, &end))
+		return 0;
+	if (unlikely(!access_ok((void __user *)start, len)))
+		return -EFAULT;
+
+	nr_pinned = lockless_pages_from_mm(start, end, gup_flags, pages);
+	if (nr_pinned == nr_pages || gup_flags & FOLL_FAST_ONLY)
+		return nr_pinned;
+
+	/* Slow path: try to get the remaining pages with get_user_pages */
+	start += nr_pinned << PAGE_SHIFT;
+	pages += nr_pinned;
+	ret = __gup_longterm_unlocked(start, nr_pages - nr_pinned, gup_flags,
+				      pages);
+	if (ret < 0) {
+		/*
+		 * The caller has to unpin the pages we already pinned so
+		 * returning -errno is not an option
+		 */
+		if (nr_pinned)
+			return nr_pinned;
+		return ret;
+	}
+	return ret + nr_pinned;
+}
+
+/**
+ * get_user_pages_fast_only() - pin user pages in memory
+ * @start:      starting user address
+ * @nr_pages:   number of pages from start to pin
+ * @gup_flags:  flags modifying pin behaviour
+ * @pages:      array that receives pointers to the pages pinned.
+ *              Should be at least nr_pages long.
+ *
  * Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to
  * the regular GUP.
  * Note a difference with get_user_pages_fast: this always returns the
@@ -2336,142 +2763,244 @@ static bool gup_fast_permitted(unsigned long start, unsigned long end)
  * access can get ambiguous page results. If you call this function without
  * 'write' set, you'd better be sure that you're ok with that ambiguity.
  */
-int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
-			  struct page **pages)
+int get_user_pages_fast_only(unsigned long start, int nr_pages,
+			     unsigned int gup_flags, struct page **pages)
 {
-	unsigned long len, end;
-	unsigned long flags;
-	int nr = 0;
+	int nr_pinned;
+	/*
+	 * Internally (within mm/gup.c), gup fast variants must set FOLL_GET,
+	 * because gup fast is always a "pin with a +1 page refcount" request.
+	 *
+	 * FOLL_FAST_ONLY is required in order to match the API description of
+	 * this routine: no fall back to regular ("slow") GUP.
+	 */
+	gup_flags |= FOLL_GET | FOLL_FAST_ONLY;
 
-	start = untagged_addr(start) & PAGE_MASK;
-	len = (unsigned long) nr_pages << PAGE_SHIFT;
-	end = start + len;
-
-	if (end <= start)
-		return 0;
-	if (unlikely(!access_ok((void __user *)start, len)))
-		return 0;
+	nr_pinned = internal_get_user_pages_fast(start, nr_pages, gup_flags,
+						 pages);
 
 	/*
-	 * Disable interrupts.  We use the nested form as we can already have
-	 * interrupts disabled by get_futex_key.
-	 *
-	 * With interrupts disabled, we block page table pages from being
-	 * freed from under us. See struct mmu_table_batch comments in
-	 * include/asm-generic/tlb.h for more details.
-	 *
-	 * We do not adopt an rcu_read_lock(.) here as we also want to
-	 * block IPIs that come from THPs splitting.
-	 *
-	 * NOTE! We allow read-only gup_fast() here, but you'd better be
-	 * careful about possible COW pages. You'll get _a_ COW page, but
-	 * not necessarily the one you intended to get depending on what
-	 * COW event happens after this. COW may break the page copy in a
-	 * random direction.
+	 * As specified in the API description above, this routine is not
+	 * allowed to return negative values. However, the common core
+	 * routine internal_get_user_pages_fast() *can* return -errno.
+	 * Therefore, correct for that here:
 	 */
+	if (nr_pinned < 0)
+		nr_pinned = 0;
 
-	if (IS_ENABLED(CONFIG_HAVE_FAST_GUP) &&
-	    gup_fast_permitted(start, end)) {
-		local_irq_save(flags);
-		gup_pgd_range(start, end, write ? FOLL_WRITE : 0, pages, &nr);
-		local_irq_restore(flags);
-	}
-
-	return nr;
+	return nr_pinned;
 }
-EXPORT_SYMBOL_GPL(__get_user_pages_fast);
-
-static int __gup_longterm_unlocked(unsigned long start, int nr_pages,
-				   unsigned int gup_flags, struct page **pages)
-{
-	int ret;
-
-	/*
-	 * FIXME: FOLL_LONGTERM does not work with
-	 * get_user_pages_unlocked() (see comments in that function)
-	 */
-	if (gup_flags & FOLL_LONGTERM) {
-		down_read(&current->mm->mmap_sem);
-		ret = __gup_longterm_locked(current, current->mm,
-					    start, nr_pages,
-					    pages, NULL, gup_flags);
-		up_read(&current->mm->mmap_sem);
-	} else {
-		ret = get_user_pages_unlocked(start, nr_pages,
-					      pages, gup_flags);
-	}
-
-	return ret;
-}
+EXPORT_SYMBOL_GPL(get_user_pages_fast_only);
 
 /**
  * get_user_pages_fast() - pin user pages in memory
- * @start:	starting user address
- * @nr_pages:	number of pages from start to pin
- * @gup_flags:	flags modifying pin behaviour
- * @pages:	array that receives pointers to the pages pinned.
- *		Should be at least nr_pages long.
+ * @start:      starting user address
+ * @nr_pages:   number of pages from start to pin
+ * @gup_flags:  flags modifying pin behaviour
+ * @pages:      array that receives pointers to the pages pinned.
+ *              Should be at least nr_pages long.
  *
- * Attempt to pin user pages in memory without taking mm->mmap_sem.
+ * Attempt to pin user pages in memory without taking mm->mmap_lock.
  * If not successful, it will fall back to taking the lock and
  * calling get_user_pages().
  *
- * Returns number of pages pinned. This may be fewer than the number
- * requested. If nr_pages is 0 or negative, returns 0. If no pages
- * were pinned, returns -errno.
+ * Returns number of pages pinned. This may be fewer than the number requested.
+ * If nr_pages is 0 or negative, returns 0. If no pages were pinned, returns
+ * -errno.
  */
 int get_user_pages_fast(unsigned long start, int nr_pages,
 			unsigned int gup_flags, struct page **pages)
 {
-	unsigned long addr, len, end;
-	int nr = 0, ret = 0;
-
-	if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM |
-				       FOLL_FORCE)))
+	if (!is_valid_gup_flags(gup_flags))
 		return -EINVAL;
 
-	start = untagged_addr(start) & PAGE_MASK;
-	addr = start;
-	len = (unsigned long) nr_pages << PAGE_SHIFT;
-	end = start + len;
-
-	if (end <= start)
-		return 0;
-	if (unlikely(!access_ok((void __user *)start, len)))
-		return -EFAULT;
-
 	/*
-	 * The FAST_GUP case requires FOLL_WRITE even for pure reads,
-	 * because get_user_pages() may need to cause an early COW in
-	 * order to avoid confusing the normal COW routines. So only
-	 * targets that are already writable are safe to do by just
-	 * looking at the page tables.
+	 * The caller may or may not have explicitly set FOLL_GET; either way is
+	 * OK. However, internally (within mm/gup.c), gup fast variants must set
+	 * FOLL_GET, because gup fast is always a "pin with a +1 page refcount"
+	 * request.
 	 */
-	if (IS_ENABLED(CONFIG_HAVE_FAST_GUP) &&
-	    gup_fast_permitted(start, end)) {
-		local_irq_disable();
-		gup_pgd_range(addr, end, gup_flags | FOLL_WRITE, pages, &nr);
-		local_irq_enable();
-		ret = nr;
-	}
-
-	if (nr < nr_pages) {
-		/* Try to get the remaining pages with get_user_pages */
-		start += nr << PAGE_SHIFT;
-		pages += nr;
-
-		ret = __gup_longterm_unlocked(start, nr_pages - nr,
-					      gup_flags, pages);
-
-		/* Have to be a bit careful with return values */
-		if (nr > 0) {
-			if (ret < 0)
-				ret = nr;
-			else
-				ret += nr;
-		}
-	}
-
-	return ret;
+	gup_flags |= FOLL_GET;
+	return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages);
 }
 EXPORT_SYMBOL_GPL(get_user_pages_fast);
+
+/**
+ * pin_user_pages_fast() - pin user pages in memory without taking locks
+ *
+ * @start:      starting user address
+ * @nr_pages:   number of pages from start to pin
+ * @gup_flags:  flags modifying pin behaviour
+ * @pages:      array that receives pointers to the pages pinned.
+ *              Should be at least nr_pages long.
+ *
+ * Nearly the same as get_user_pages_fast(), except that FOLL_PIN is set. See
+ * get_user_pages_fast() for documentation on the function arguments, because
+ * the arguments here are identical.
+ *
+ * FOLL_PIN means that the pages must be released via unpin_user_page(). Please
+ * see Documentation/core-api/pin_user_pages.rst for further details.
+ */
+int pin_user_pages_fast(unsigned long start, int nr_pages,
+			unsigned int gup_flags, struct page **pages)
+{
+	/* FOLL_GET and FOLL_PIN are mutually exclusive. */
+	if (WARN_ON_ONCE(gup_flags & FOLL_GET))
+		return -EINVAL;
+
+	gup_flags |= FOLL_PIN;
+	return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages);
+}
+EXPORT_SYMBOL_GPL(pin_user_pages_fast);
+
+/*
+ * This is the FOLL_PIN equivalent of get_user_pages_fast_only(). Behavior
+ * is the same, except that this one sets FOLL_PIN instead of FOLL_GET.
+ *
+ * The API rules are the same, too: no negative values may be returned.
+ */
+int pin_user_pages_fast_only(unsigned long start, int nr_pages,
+			     unsigned int gup_flags, struct page **pages)
+{
+	int nr_pinned;
+
+	/*
+	 * FOLL_GET and FOLL_PIN are mutually exclusive. Note that the API
+	 * rules require returning 0, rather than -errno:
+	 */
+	if (WARN_ON_ONCE(gup_flags & FOLL_GET))
+		return 0;
+	/*
+	 * FOLL_FAST_ONLY is required in order to match the API description of
+	 * this routine: no fall back to regular ("slow") GUP.
+	 */
+	gup_flags |= (FOLL_PIN | FOLL_FAST_ONLY);
+	nr_pinned = internal_get_user_pages_fast(start, nr_pages, gup_flags,
+						 pages);
+	/*
+	 * This routine is not allowed to return negative values. However,
+	 * internal_get_user_pages_fast() *can* return -errno. Therefore,
+	 * correct for that here:
+	 */
+	if (nr_pinned < 0)
+		nr_pinned = 0;
+
+	return nr_pinned;
+}
+EXPORT_SYMBOL_GPL(pin_user_pages_fast_only);
+
+/**
+ * pin_user_pages_remote() - pin pages of a remote process
+ *
+ * @mm:		mm_struct of target mm
+ * @start:	starting user address
+ * @nr_pages:	number of pages from start to pin
+ * @gup_flags:	flags modifying lookup behaviour
+ * @pages:	array that receives pointers to the pages pinned.
+ *		Should be at least nr_pages long. Or NULL, if caller
+ *		only intends to ensure the pages are faulted in.
+ * @vmas:	array of pointers to vmas corresponding to each page.
+ *		Or NULL if the caller does not require them.
+ * @locked:	pointer to lock flag indicating whether lock is held and
+ *		subsequently whether VM_FAULT_RETRY functionality can be
+ *		utilised. Lock must initially be held.
+ *
+ * Nearly the same as get_user_pages_remote(), except that FOLL_PIN is set. See
+ * get_user_pages_remote() for documentation on the function arguments, because
+ * the arguments here are identical.
+ *
+ * FOLL_PIN means that the pages must be released via unpin_user_page(). Please
+ * see Documentation/core-api/pin_user_pages.rst for details.
+ */
+long pin_user_pages_remote(struct mm_struct *mm,
+			   unsigned long start, unsigned long nr_pages,
+			   unsigned int gup_flags, struct page **pages,
+			   struct vm_area_struct **vmas, int *locked)
+{
+	/* FOLL_GET and FOLL_PIN are mutually exclusive. */
+	if (WARN_ON_ONCE(gup_flags & FOLL_GET))
+		return -EINVAL;
+
+	gup_flags |= FOLL_PIN;
+	return __get_user_pages_remote(mm, start, nr_pages, gup_flags,
+				       pages, vmas, locked);
+}
+EXPORT_SYMBOL(pin_user_pages_remote);
+
+/**
+ * pin_user_pages() - pin user pages in memory for use by other devices
+ *
+ * @start:	starting user address
+ * @nr_pages:	number of pages from start to pin
+ * @gup_flags:	flags modifying lookup behaviour
+ * @pages:	array that receives pointers to the pages pinned.
+ *		Should be at least nr_pages long. Or NULL, if caller
+ *		only intends to ensure the pages are faulted in.
+ * @vmas:	array of pointers to vmas corresponding to each page.
+ *		Or NULL if the caller does not require them.
+ *
+ * Nearly the same as get_user_pages(), except that FOLL_TOUCH is not set, and
+ * FOLL_PIN is set.
+ *
+ * FOLL_PIN means that the pages must be released via unpin_user_page(). Please
+ * see Documentation/core-api/pin_user_pages.rst for details.
+ */
+long pin_user_pages(unsigned long start, unsigned long nr_pages,
+		    unsigned int gup_flags, struct page **pages,
+		    struct vm_area_struct **vmas)
+{
+	/* FOLL_GET and FOLL_PIN are mutually exclusive. */
+	if (WARN_ON_ONCE(gup_flags & FOLL_GET))
+		return -EINVAL;
+
+	gup_flags |= FOLL_PIN;
+	return __gup_longterm_locked(current->mm, start, nr_pages,
+				     pages, vmas, gup_flags);
+}
+EXPORT_SYMBOL(pin_user_pages);
+
+/*
+ * pin_user_pages_unlocked() is the FOLL_PIN variant of
+ * get_user_pages_unlocked(). Behavior is the same, except that this one sets
+ * FOLL_PIN and rejects FOLL_GET.
+ */
+long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
+			     struct page **pages, unsigned int gup_flags)
+{
+	/* FOLL_GET and FOLL_PIN are mutually exclusive. */
+	if (WARN_ON_ONCE(gup_flags & FOLL_GET))
+		return -EINVAL;
+
+	gup_flags |= FOLL_PIN;
+	return get_user_pages_unlocked(start, nr_pages, pages, gup_flags);
+}
+EXPORT_SYMBOL(pin_user_pages_unlocked);
+
+/*
+ * pin_user_pages_locked() is the FOLL_PIN variant of get_user_pages_locked().
+ * Behavior is the same, except that this one sets FOLL_PIN and rejects
+ * FOLL_GET.
+ */
+long pin_user_pages_locked(unsigned long start, unsigned long nr_pages,
+			   unsigned int gup_flags, struct page **pages,
+			   int *locked)
+{
+	/*
+	 * FIXME: Current FOLL_LONGTERM behavior is incompatible with
+	 * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
+	 * vmas.  As there are no users of this flag in this call we simply
+	 * disallow this option for now.
+	 */
+	if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
+		return -EINVAL;
+
+	/* FOLL_GET and FOLL_PIN are mutually exclusive. */
+	if (WARN_ON_ONCE(gup_flags & FOLL_GET))
+		return -EINVAL;
+
+	gup_flags |= FOLL_PIN;
+	return __get_user_pages_locked(current->mm, start, nr_pages,
+				       pages, NULL, locked,
+				       gup_flags | FOLL_TOUCH);
+}
+EXPORT_SYMBOL(pin_user_pages_locked);